An entry point for running brain-imaging prediction and analysis models. It identifies the requested model, selects its instructions, and coordinates the MRI or fMRI preparation needed beforehand.

It helps browse model options, match inputs and outputs, prepare fMRI or structural MRI data, and route tasks such as classification, regression, clustering, or signal analysis.

It helps researchers choose the right model workflow and keep data preparation connected to the analysis they want to run.

run_models — Skill for Claude Code and Codex by CUHK-AIM-Group

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add CUHK-AIM-Group/NeuroClaw --skill run_models

Clone the repo

git clone --depth 1 https://github.com/CUHK-AIM-Group/NeuroClaw

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/run_models/github.svg)](https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/run_models)

Your own site

<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/run_models"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/run_models/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/run_models"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/run_models.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,000 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 36 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Agent Snooping · line 48
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 49
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 50
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 51
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 52
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 101
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 263
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 53
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 103
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 54
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 105
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 55
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 107
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 56
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 112
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 57
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 114
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 58
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 116
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 59
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.06000
Opus 5	$0.00032	$0.03000
Sonnet 5	$0.00013	$0.01200
Haiku 4.5	$0.00006	$0.00600

Measured 6d ago against content hash 8a929540697d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

run_models scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/run_models/SKILL.md · 496 lines

How it starts

The opening of the file, as written. The whole thing — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run Models Skill (Model Entry Layer)

Overview

run_models is the NeuroClaw entry skill for model-level inference workflows.

This skill is responsible for:

Maintaining a model registry (name, paper, source code, input/output, doc file path)
Selecting the correct model skill under skills/<model-name>/SKILL.md
Coordinating required data preparation before model execution
Delegating modality preprocessing to fmri-skill and smri-skill

It supports both:

deep learning model routes for phenotype prediction
non-deep-learning statistical / unsupervised / classical machine-learning routes such as first-level and second-level task-fMRI GLM, resting-state ICA, resting-state DictLearning, disease classification with SVM, disease classification with SpaceNet, brain parcellation with K-means, brain parcellation with Hierarchical clustering, temporal filtering, and detrending

This skill does not hardcode detailed install/run commands for each model. Those details are stored in model-specific markdown files.

Research use only.

Core Workflow (Never Bypassed)

Identify requested model and task (classification/regression phenotype prediction).
Locate the corresponding model skill under skills/<model-name>/SKILL.md.
Verify required inputs (ROI features, optional sMRI features).
If inputs are not ready, delegate preprocessing to modality skills:
- fmri-skill for ROI extraction from fMRI
- smri-skill when model additionally requires structural features
Generate a numbered execution plan and wait for explicit user confirmation (YES / execute / proceed).
On confirmation, execute via claw-shell following model doc instructions.

Model Registry (Current)

Model	Paper	Code	Input	Output	Model Doc
BrainGNN	Li et al., 2020, Braingnn: Interpretable brain graph neural network for fmri analysis	https://github.com/xxlya/BrainGNN_Pytorch/tree/main	fMRI ROI features (graph/node-level ROI representation)	Phenotype prediction (classification/regression) + interpretable graph indicators	`skills/brain_gnn/SKILL.md`
BNT	Kan et al., 2022, BrainNetworkTransformer	https://github.com/Wayfear/BrainNetworkTransformer	fMRI ROI FC matrix (dense [N, N], no PyG)	Phenotype prediction (classification/regression) + attention weights + DEC cluster assignments	`skills/bnt/SKILL.md`
BrainNetCNN	Kawahara et al., 2017, BrainNetCNN	https://github.com/jeremykawahara/brainnetcnn	Dense ROI connectivity matrix [N, N]	Phenotype classification/regression with E2E, E2N, and N2G convolutions	`skills/brainnetcnn/SKILL.md`
FM-APP	He et al., 2024, FM-APP: Foundation model for any phenotype prediction via fMRI to sMRI knowledge transfer	https://github.com/ZhibinHe/FM-APP	fMRI ROI features + sMRI features	Phenotype prediction (any-phenotype setting)	`skills/fm_app/SKILL.md`
NeuroStorm	NeuroClaw model entry for storm-related phenotype prediction workflows	see `skills/neurostorm/SKILL.md`	Multi-modal neuroimaging features as specified in the model doc	Phenotype prediction / downstream inference as specified in the model doc	`skills/neurostorm/SKILL.md`
GLM	Classical first-level and second-level task-fMRI general linear model	Nilearn / SPM-style implementation route	Preprocessed task fMRI, events, optional confounds, and optional subject-level contrast maps for group inference	Task activation contrasts, group z maps, and statistical inference outputs	`skills/glm/SKILL.md`
ICA	Classical resting-state network decomposition method	Nilearn decomposition implementation route	Preprocessed resting-state fMRI, optional mask, optional confounds	Intrinsic connectivity component maps, subject time series, optional connectomes	`skills/ica/SKILL.md`
DictLearning	Classical sparse resting-state network decomposition method	Nilearn decomposition implementation route	Preprocessed resting-state fMRI, optional mask, optional confounds	Sparse component maps, subject time series, optional connectomes	`skills/dictlearning/SKILL.md`
SpaceNet	Classical voxel-wise disease classification method for neuroimaging	Nilearn decoding implementation route	Aligned voxel maps, labels, optional covariates, optional mask	Predicted labels, decision scores, CV metrics, coefficient maps	`skills/spacenet/SKILL.md`
K-means	Classical brain parcellation method for neuroimaging	Nilearn / clustering-based parcellation route	Preprocessed feature maps or image lists, optional mask, requested parcel count	Parcel labels, cluster summaries, optional centroid outputs	`skills/kmeans/SKILL.md`
Hierarchical	Classical hierarchical brain parcellation method for neuroimaging	Nilearn / clustering-based parcellation route	Preprocessed feature maps or image lists, optional mask, requested parcel count	Parcel labels, cluster summaries, optional dendrogram outputs	`skills/hierarchical/SKILL.md`
Filtering	Classical signal denoising method for neuroimaging time series	Nilearn / preprocessing route	Preprocessed BOLD image or time series, TR, optional confounds, optional mask	Denoised BOLD, cleaned time series, optional QC summaries	`skills/filtering/SKILL.md`
Detrending	Classical signal denoising method for neuroimaging time series	Nilearn / preprocessing route	Preprocessed BOLD image or time series, TR, optional confounds, optional mask	Cleaned BOLD, cleaned time series, optional QC summaries	`skills/detrending/SKILL.md`
Statistical ML	OLS, logistic/Ridge/Elastic Net, SVM/SVR, XGBoost, MixedLM	NeuroClaw unified tabular trainer	Subject-level tabular/ROI features	Fold-local predictions, inference, metrics	`skills/statistical-ml/SKILL.md`
Subject Subtyping	K-means, GMM, spectral, NMF, consensus, autoencoder	NeuroClaw subtyping trainer	Subject-level feature matrix	Subtype labels, embeddings, stability metrics	`skills/subject-subtyping/SKILL.md`
Survival Models	Cox, RSF, DeepSurv, XGBoost survival	NeuroClaw censor-aware trainer	Features, duration, event	Risk scores, concordance	`skills/survival-models/SKILL.md`
Causal Treatment	Meta-learners, DR, causal forest, TARNet, DragonNet	NeuroClaw cross-fitted causal trainer	Features, treatment, outcome	CATE, treatment policy, policy value	`skills/causal-treatment-models/SKILL.md`
Temporal Models	LSTM, GRU, TCN, Transformer	NeuroClaw PyTorch trainer	Subject sequences	Classification/regression predictions	`skills/temporal-models/SKILL.md`
Imaging Genetics	GWAS/PRS, PLS, CCA	PLINK2 + NeuroClaw matrix trainer	Genotype and imaging phenotype	Associations and latent scores	`skills/imaging-genetics-models/SKILL.md`
CNN3D	Compact residual 3D CNN	NeuroClaw PyTorch trainer	Subject volumes	Predictions and checkpoints	`skills/cnn3d/SKILL.md`
CPM	Connectome Predictive Modeling	NeuroClaw CPM trainer	FC matrices/vectors and labels	Fold-local predictions and selected-network models	`skills/cpm/SKILL.md`
KG Link Prediction	ComplEx, R-GCN, GraphSAGE, GAT	NeuroOracle/PyG	Knowledge-graph triples	Triple scores and embeddings	`skills/kg-link-prediction/SKILL.md`

Read the full file on GitHub · 496 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago First seen · 496 lines · 64 tokens per session scan A 8a929540697d

Subscribe to this mod's changes

run_models is a skill published in the GitHub repository CUHK-AIM-Group/NeuroClaw (83 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 6,000 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Planning Scientific

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens